similar to: making makepredictcall() work

Hi all, Very surprising (to me!) and mystifying result from predict.glm(): the predictions vary depending on whether or not I use ns() or splines::ns(). Reprex follows: library(splines) set.seed(12345) dat <- data.frame(claim = rbinom(1000, 1, 0.5)) mns <- c(3.4, 3.6) sds <- c(0.24, 0.35) dat$wind <- exp(rnorm(nrow(dat), mean = mns[dat$claim + 1], sd = sds[dat$claim + 1])) dat <-

On 27/04/2018 9:25 AM, Hadley Wickham wrote: > Hi all, > > Very surprising (to me!) and mystifying result from predict.glm(): the > predictions vary depending on whether or not I use ns() or > splines::ns(). Reprex follows: > > library(splines) > > set.seed(12345) > dat <- data.frame(claim = rbinom(1000, 1, 0.5)) > mns <- c(3.4, 3.6) > sds <- c(0.24,

An issue came up with the rms package today that makepredictcall would solve, and I was going to suggest it to the author. But looking in the help documents I couldn't find any reference to it. There is a manual page, but it does not give much aid in creating code for a new transformation function. Did I miss something? If not, I'd be willing to draft a paragraph about that which

That site, and that document in particular, had nothing to add on this particular topic. So on to question 2. I think the material is useful. If I write it up will that be welcome/tolerated/ignored addition to the R docs? On 03/07/2014 05:00 AM, r-devel-request at r-project.org wrote: > See the developer site, e.g. > http://developer.r-project.org/model-fitting-functions.txt . >

Apologies if this is this too obscure for R-help. In package splines, ns(x,,knots,intercept=TRUE) produces an n by K+2 matrix N, the values of K+2 basis functions for the natural splines with K (internal) knots, evaluated at x. It does this by first generating an n by K+4 matrix B of unconstrained splines, then postmultiplying B by H, a K+4 by K+2 representation of the nullspace of C (2 by K+4),

On 08/02/2012 05:00 AM, r-devel-request at r-project.org wrote: > Now I just have to grovel over the R code in ns() and bs() to figure > out how exactly they pick knots and handle boundary conditions, plus > there is some code that I don't understand in ns() that uses qr() to > postprocess the output from spline.des. I assume this is involved > somehow in imposing the boundary

Hi, I'm using natural cubic splines from splines::ns() in survival regression (regressing inter-arrival times of patients to a queue on queue size). The queue size fluctuates between 3600 and 3900. I would like to be able to run predict.survreg() for sizes <3600 and >3900 by assuming that the rate for <3600 is the same as for 3600 and that for >4000 it's the same as for

Hello. I seem to be having the same problem that Paul had in the thread titled "[Rd] R 2.15.2 make check failure on 32-bit --with-blas="-lgoto2"" from October of last year <https://stat.ethz.ch/pipermail/r-devel/2012-October/065103.html> Unfortunately, that thread ended without an answer to his last question. Briefly, I am trying to compile an Rblas for Windows NT 32bit

Goodmorning, This is a documentation related question about the B-spline function in R. In the help file it is stated that: "df degrees of freedom; one can specify df rather than knots; bs() then chooses df-degree-1 knots at suitable quantiles of x (which will ignore missing values)." So if one were to specify a spline with 6 degrees of freedom (and no intercept) then a basis

Below is an example of a problem I encounter repeatedly when I write functions. A call works at the command line, but it does not work inside a function, even when I have made sure that all required variables are available within the function. The only way I know to solve it is to make the required variable global, which of course is dangerous. What is the elegant or appropriate way to solve

Dear List, I'm using gam in a multiple imputation framework -- specifying the knot locations, and saving the results of multiple models, each of which is fit with slightly different data (because some of it is predicted when missing). In MI, coefficients from multiple models are averaged, as are variance-covariance matrices. VCV's get an additional correction to account for how

Hi, I use a mboost model to predict my dependent variable on new data. I get the following warning message: In bs(mf[[i]], knots = args$knots[[i]]$knots, degree = args$degree, : some 'x' values beyond boundary knots may cause ill-conditioned bases The new predicted values are partly negative although the variable in the training data ranges from 3 to 8 on a numeric scale. In order to

Dear Rusers, I am now using R and SAS to fit the piecewise linear functions, and what surprised me is that they have a great differrent result. See below. #R code--Knots for distance are 16.13 and 24, respectively, and Knots for y are -0.4357 and -0.3202 m.glm<-glm(mark~x+poly(elevation,2)+bs(distance,degree=1,knots=c(16.13,24)) +bs(y,degree=1,knots=c(-0.4357,-0.3202

Dear R-help, In the rms package, I have fitted an ols model with a variable represented as a restricted cubic spline, with the knot locations specified as a previously defined vector. When I save the model object and open it in another workspace which does not contain the vector of knot locations, I get an error message if I try to predict with that model. This also happens if only one workspace

Dear, When fitting the following model knots <- 5 lrm.NDWI <- lrm(m.arson ~ rcs(NDWI,knots) I obtain the following result: Logistic Regression Model lrm(formula = m.arson ~ rcs(NDWI, knots)) Frequencies of Responses 0 1 666 35 Obs Max Deriv Model L.R. d.f. P C Dxy Gamma Tau-a R2 Brier 701 5e-07 34.49

When I do: > apc <- glm( D ~ ns( Ax, knots=seq(50,80,10), Bo=c(40,90) ) + + ns( Cx, knots=seq(1880,1940,20), Bo=c(1840,1960) ) + + ns( Px, knots=seq(1960,1980,10), Bo=c(1940,2000) ) + + offset( log( Y ) ), + family=poisson ) > pterm <- predict( apc, type="terms" ) > plink <- predict( apc,

Dear List, I'm using GAMs in a multiple imputation project, and I want to be able to combine the parameter estimates and covariance matrices from each completed dataset's fitted model in the end. In order to do this, I need the knots to be uniform for each model with partially-imputed data. I want to specify these knots based on the quantiles of the unique values of the non-missing

Hi all, I have a vector of proportions (post_op_prw) such that >summary(amb$post_op_prw) Min. 1st Qu. Median Mean 3rd Qu. Max. NA's 0.0000 0.0000 0.0000 0.3985 0.9134 0.9962 1.0000 > summary(cut2(amb$post_op_prw,0.0001)) [0.0000,0.0001) [0.0001,0.9962] NA's 1904 1672 1

all.vars works fine, EXCEPT, it give a bit too much. I only want the regression variables, but in the following example I also get "k" the variable holding the chosen knots. Any machinery to find only "real" regression variables? cheers, Bendix library( splines ) y <- rnorm(100) x <- rnorm(100) k <- -1:1 ml <- lm( y ~ bs(x,knots=k) ) mg <- glm( y ~

Hi, I have a question about the usage of eval(). Wonder if any experienced user can help me out of it. I use eval() in the following function: semireg.pwl <- function(coef.s=rnorm(1),coef.a=rnorm(1),knots.pos=knots.x,knots.ini.val=knots.val){ knotn <- length(knots.pos) def.par.env <- sys.frame(1) print(def.par.env) print(environment(coef.s)) tg <- eval( (parse(text=